feat: add Zhipu AI (GLM) model provider support

Adds zhipuai as a new provider using the OpenAI-compatible API at
api.z.ai. Supports api_key config or ZHIPUAI_API_KEY env var, with
optional endpoint override.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

CHANGELOG.md

@@ -6,6 +6,10 @@ All notable changes to Flynn are documented in this file.
 
 ### Added
 
+- **Zhipu AI (GLM) Provider** -- Support for Zhipu AI's GLM models (glm-4.5, glm-4.7, etc.)
+  via their OpenAI-compatible API at `https://api.z.ai/api/paas/v4`. Uses `provider: zhipuai`
+  in config with `api_key` or `ZHIPUAI_API_KEY` env var.
+
 - **Agent Tool: file.patch** -- Multi-file, multi-hunk structured patch tool. Apply
   line-based replacements, insertions, and deletions across multiple files in a single
   tool call. Hunks are applied bottom-up to preserve line numbers. 10 tests.

README.md

@@ -5,7 +5,7 @@ Self-hosted personal AI assistant with Telegram and Terminal interfaces.
 ## Features
 
 - **Multi-Frontend**: Telegram bot + Terminal UI (minimal & fullscreen modes) + Web UI dashboard
-- **Multi-Model**: Anthropic Claude, OpenAI, GitHub Copilot, Gemini, Bedrock, Ollama, llama.cpp with intelligent routing
+- **Multi-Model**: Anthropic Claude, OpenAI, GitHub Copilot, Gemini, Bedrock, Zhipu AI (GLM), Ollama, llama.cpp with intelligent routing
 - **Multi-Channel**: Telegram, Discord, Slack, WhatsApp with unified adapter interface
 - **Web Dashboard**: SPA control panel with health monitoring, chat, session browser, and settings editor
 - **Model Switching**: Switch between cloud/local models on demand
@@ -113,6 +113,7 @@ hooks:
 | Gemini | `provider: gemini`, `api_key` |
 | Bedrock | `provider: bedrock`, AWS credentials |
 | Ollama | `provider: ollama`, `model`, optional `endpoint` |
+| Zhipu AI (GLM) | `provider: zhipuai`, `api_key` or `ZHIPUAI_API_KEY`, optional `endpoint` |
 | llama.cpp | `provider: llamacpp`, `endpoint` |
 
 ### Model Tiers

src/config/schema.ts

@@ -19,7 +19,7 @@ const serverSchema = z.object({
 });
 
 const modelConfigBaseSchema = z.object({
-  provider: z.enum(['anthropic', 'openai', 'gemini', 'ollama', 'llamacpp', 'openrouter', 'bedrock', 'github']),
+  provider: z.enum(['anthropic', 'openai', 'gemini', 'ollama', 'llamacpp', 'openrouter', 'bedrock', 'github', 'zhipuai']),
   model: z.string(),
   endpoint: z.string().optional(),
   api_key: z.string().optional(),

src/daemon/clientFactory.test.ts

@@ -87,6 +87,15 @@ describe('createClientFromConfig', () => {
     expect(client).toBeInstanceOf(OpenAIClient);
   });
 
+  it('creates OpenAIClient with Zhipu AI baseURL for zhipuai provider', () => {
+    const client = createClientFromConfig({
+      provider: 'zhipuai',
+      model: 'glm-4.5',
+      api_key: 'test-key',
+    });
+    expect(client).toBeInstanceOf(OpenAIClient);
+  });
+
   it('creates BedrockClient for bedrock provider', () => {
     const client = createClientFromConfig({
       provider: 'bedrock',

src/daemon/index.ts

@@ -108,6 +108,12 @@ export function createClientFromConfig(cfg: ModelConfig): ModelClient {
         apiKey: cfg.api_key ?? process.env.OPENROUTER_API_KEY,
         baseURL: cfg.endpoint ?? 'https://openrouter.ai/api/v1',
       });
+    case 'zhipuai':
+      return new OpenAIClient({
+        model: cfg.model,
+        apiKey: cfg.api_key ?? process.env.ZHIPUAI_API_KEY,
+        baseURL: cfg.endpoint ?? 'https://api.z.ai/api/paas/v4',
+      });
     case 'bedrock':
       return new BedrockClient({
         model: cfg.model,